Related Experiment Video
Updated: Jan 7, 2026
05:33
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
741
Seeing Beyond the Microscope: Artificial Intelligence and Fluorescence Confocal Digital Imaging in Pediatric Surgical
Donatella Di Fabrizio1, Gloria Daziani2, Ilir Qose3
1Pediatric Surgery Unit, Salesi Children's Hospital, Polytechnic University of Marche, 60123 Ancona, Italy.
Children (Basel, Switzerland)
|December 30, 2025
Summary
Large language models (LLMs) show promise in pediatric digital pathology, aiding rapid diagnosis with fluorescence confocal microscopy (FCM) images. Adding immunohistochemistry (IHC) data significantly improves diagnostic accuracy in complex cases.
Area of Science:
- Pathology
- Artificial Intelligence
- Medical Imaging
Background:
- Digital pathology (DP) and fluorescence confocal microscopy (FCM) enable rapid, specimen-preserving tissue assessment.
- The application of AI and LLMs in pediatric surgical pathology diagnostics remains largely unexplored.
- This study investigates the utility of LLMs in intraoperative pediatric surgical pathology.
Purpose of the Study:
- To evaluate the diagnostic performance of two commercial LLMs (GPT-4V and Claude 3.7 Sonnet) in pediatric surgical pathology using ex vivo FCM images.
- To assess the impact of immunohistochemistry (IHC) data on LLM diagnostic accuracy.
- To explore the potential of AI-assisted workflows in enhancing pediatric surgical pathology diagnostics.
Main Methods:
- A prospective, single-center study of 20 pediatric surgical cases with intraoperative ex vivo FCM imaging.
- Two LLMs, AnPathology-Gpt (GPT-4V) and AnPathology Project (Claude 3.7 Sonnet), were prompted to generate diagnostic reports with and without IHC data.
- LLM outputs were compared to a gold standard diagnosis by a pediatric pathologist, evaluating accuracy, sensitivity, specificity, and Cohen's kappa.
Main Results:
- AnPathology-Gpt achieved 85% accuracy (κ=0.78), and AnPathology Project achieved 80% accuracy (κ=0.63) across all cases.
- Both models demonstrated 100% sensitivity for neoplastic cases, with errors primarily in non-neoplastic lesions.
- Inclusion of IHC data improved accuracy from 40% to 80% and sensitivity from 50% to 100% for both models in a subset of 5 cases.
Conclusions:
- Multimodal LLMs can support accurate and rapid diagnosis in pediatric digital pathology.
- The integration of IHC data enhances LLM performance in diagnostically challenging pediatric surgical pathology cases.
- Further multicenter studies are necessary to validate these findings and establish AI's role in pediatric surgical pathology workflows.
Keywords:
artificial intelligencechildrendigital pathologyex vivo fluorescence confocal microscopylarge language modelsMore Related Videos
Related Concept Videos
01:16Confocal Fluorescence Microscopy
19.9K
Confocal microscopy is an advanced microscopic technique. The prime advantage of the confocal microscope over other microscopy techniques is its ability to block the out-of-focus light from the illuminated samples using pinholes. It is widely used with fluorescence optics to obtain high-resolution, sharp contrast images. Unlike optical microscopes, confocal microscopes use a focused beam of light laser to scan the entire sample surface at different z-planes. These microscopes are, therefore,...
19.9K
01:28Three-Dimensional Microscopy in Microbiology
732
Three-dimensional imaging techniques are essential in cell biology, allowing researchers to visualize intricate cellular structures with high resolution. Two prominent methods, Differential Interference Contrast Microscopy (DIC) and Confocal Scanning Laser Microscopy (CSLM), provide distinct advantages for imaging live and thick specimens, respectively.Differential Interference Contrast MicroscopyDIC microscopy enhances contrast in transparent, unstained samples by converting phase...
732
01:37Super-resolution Fluorescence Microscopy
12.1K
Super-resolution fluorescence microscopy (SRFM) provides a better resolution than conventional fluorescence microscopy by reducing the point spread function (PSF). PSF is the light intensity distribution from a point that causes it to appear blurred. Due to PSF, each fluorescing point appears bigger than its actual size, and it is the PSF interference of nearby fluorophores that causes the blurred image. Various approaches to achieving higher resolution through SRFM have recently been...
12.1K
01:29Two-Dimensional Microscopy in Microbiology
1.0K
Two-dimensional (2D) microscopy encompasses a range of optical techniques that capture images within a single focal plane, offering detailed representations of microscopic structures. These techniques are essential in biological and medical research, enabling the visualization of cellular and subcellular structures with different levels of contrast and specificity.There are several major types of 2D microscopy, each with strengths and applications.Bright-Field MicroscopyBright-field microscopy...
1.0K
01:12Immunofluorescence Microscopy
12.8K
A fluorescence microscope uses fluorescent chromophores called fluorochromes, which can absorb energy from a light source and then emit this energy as visible light. Fluorochromes include naturally fluorescent substances (such as chlorophylls) and fluorescent stains that are added to the specimen to create contrast. Dyes such as Texas red and FITC are examples of fluorochromes. Other examples include the nucleic acid dyes 4’,6’-diamidino-2-phenylindole (DAPI), and acridine orange.
12.8K